Inference › Drivers / Frameworks / Toolkits › NVIDIA / CUDA v
NVIDIA driver regression for Phi

Thread Rating:
  • 0 Vote(s) - 0 Average
  • 1
  • 2
  • 3
  • 4
  • 5
Linear Mode
NVIDIA driver regression for Phi
torchshed Offline
Junior Member
**
Posts: 47
Threads: 6
Joined: Sep 2026
Reputation: 0
#2
10-16-2026, 05:35 AM
My first guess would be this: If you're on TensorRT-LLM, I'd confirm the version first and then reduce variables until the behavior is obvious. Not glamorous advice, but repeatable baselines save a lot of time.
Find
Reply


Messages In This Thread
NVIDIA driver regression for Phi - by edgecoast - 10-16-2026, 04:05 AM
Re: NVIDIA driver regression for Phi - by torchshed - 10-16-2026, 05:35 AM

Forum Jump:


Users browsing this thread: 1 Guest(s)